From 867d549fcedfac3116451129ee2f173c376cb2e4 Mon Sep 17 00:00:00 2001 From: Dale Johannesen Date: Thu, 2 Oct 2008 18:53:47 +0000 Subject: [PATCH] Handle some 64-bit atomics on x86-32, some of the time. llvm-svn: 56963 --- llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp | 27 +- llvm/lib/Target/X86/X86ISelDAGToDAG.cpp | 33 + llvm/lib/Target/X86/X86ISelLowering.cpp | 237 ++++- llvm/lib/Target/X86/X86ISelLowering.h | 20 + llvm/lib/Target/X86/X86InstrInfo.td | 47 +- .../CodeGen/X86/2008-10-02-Atomics32-2.ll | 969 ++++++++++++++++++ llvm/utils/TableGen/CodeGenInstruction.cpp | 3 +- 7 files changed, 1316 insertions(+), 20 deletions(-) create mode 100644 llvm/test/CodeGen/X86/2008-10-02-Atomics32-2.ll diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp index 0a0a06bb0067..243b21c39d6b 100644 --- a/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp @@ -6212,21 +6212,26 @@ void SelectionDAGLegalize::ExpandOp(SDValue Op, SDValue &Lo, SDValue &Hi){ break; } - // FIXME: should the LOAD_BIN and SWAP atomics get here too? Probably. - case ISD::ATOMIC_CMP_SWAP_8: - case ISD::ATOMIC_CMP_SWAP_16: - case ISD::ATOMIC_CMP_SWAP_32: + case ISD::ATOMIC_LOAD_ADD_64: + case ISD::ATOMIC_LOAD_SUB_64: + case ISD::ATOMIC_LOAD_AND_64: + case ISD::ATOMIC_LOAD_OR_64: + case ISD::ATOMIC_LOAD_XOR_64: + case ISD::ATOMIC_LOAD_NAND_64: + case ISD::ATOMIC_SWAP_64: case ISD::ATOMIC_CMP_SWAP_64: { - SDValue Tmp = TLI.LowerOperation(Op, DAG); - assert(Tmp.getNode() && "Node must be custom expanded!"); - ExpandOp(Tmp.getValue(0), Lo, Hi); - AddLegalizedOperand(SDValue(Node, 1), // Remember we legalized the chain. - LegalizeOp(Tmp.getValue(1))); + SDValue In2Lo, In2Hi, In2; + ExpandOp(Op.getOperand(2), In2Lo, In2Hi); + In2 = DAG.getNode(ISD::BUILD_PAIR, VT, In2Lo, In2Hi); + SDValue Result = TLI.LowerOperation( + DAG.getNode(Op.getOpcode(), VT, Op.getOperand(0), Op.getOperand(1), In2), + DAG); + ExpandOp(Result.getValue(0), Lo, Hi); + // Remember that we legalized the chain. + AddLegalizedOperand(SDValue(Node,1), LegalizeOp(Result.getValue(1))); break; } - - // These operators cannot be expanded directly, emit them as calls to // library functions. case ISD::FP_TO_SINT: { diff --git a/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp b/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp index ea3dbad0eeff..a60b13ef0813 100644 --- a/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp +++ b/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp @@ -160,6 +160,7 @@ namespace { private: SDNode *Select(SDValue N); + SDNode *SelectAtomic64(SDNode *Node, unsigned Opc); bool MatchAddress(SDValue N, X86ISelAddressMode &AM, bool isRoot = true, unsigned Depth = 0); @@ -1205,6 +1206,25 @@ SDNode *X86DAGToDAGISel::getTruncateTo8Bit(SDValue N0) { MVT::i8, N0, SRIdx, N0.getValue(1)); } +SDNode *X86DAGToDAGISel::SelectAtomic64(SDNode *Node, unsigned Opc) { + SDValue Chain = Node->getOperand(0); + SDValue In1 = Node->getOperand(1); + SDValue In2L = Node->getOperand(2); + SDValue In2H = Node->getOperand(3); + SDValue Tmp0, Tmp1, Tmp2, Tmp3; + if (!SelectAddr(In1, In1, Tmp0, Tmp1, Tmp2, Tmp3)) + return NULL; + AddToISelQueue(Tmp0); + AddToISelQueue(Tmp1); + AddToISelQueue(Tmp2); + AddToISelQueue(Tmp3); + AddToISelQueue(In2L); + AddToISelQueue(In2H); + AddToISelQueue(Chain); + SDValue LSI = CurDAG->getMemOperand(cast(In1)->getMemOperand()); + const SDValue Ops[] = { Tmp0, Tmp1, Tmp2, Tmp3, In2L, In2H, LSI, Chain }; + return CurDAG->getTargetNode(Opc, MVT::i32, MVT::i32, MVT::Other, Ops, 8); +} SDNode *X86DAGToDAGISel::Select(SDValue N) { SDNode *Node = N.getNode(); @@ -1277,6 +1297,19 @@ SDNode *X86DAGToDAGISel::Select(SDValue N) { break; } + case X86ISD::ATOMOR64_DAG: + return SelectAtomic64(Node, X86::ATOMOR6432); + case X86ISD::ATOMXOR64_DAG: + return SelectAtomic64(Node, X86::ATOMXOR6432); + case X86ISD::ATOMADD64_DAG: + return SelectAtomic64(Node, X86::ATOMADD6432); + case X86ISD::ATOMSUB64_DAG: + return SelectAtomic64(Node, X86::ATOMSUB6432); + case X86ISD::ATOMNAND64_DAG: + return SelectAtomic64(Node, X86::ATOMNAND6432); + case X86ISD::ATOMAND64_DAG: + return SelectAtomic64(Node, X86::ATOMAND6432); + case ISD::SMUL_LOHI: case ISD::UMUL_LOHI: { SDValue N0 = Node->getOperand(0); diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp index 3bff205b991c..f65167bd8877 100644 --- a/llvm/lib/Target/X86/X86ISelLowering.cpp +++ b/llvm/lib/Target/X86/X86ISelLowering.cpp @@ -302,6 +302,16 @@ X86TargetLowering::X86TargetLowering(X86TargetMachine &TM) setOperationAction(ISD::ATOMIC_LOAD_SUB_32, MVT::i32, Custom); setOperationAction(ISD::ATOMIC_LOAD_SUB_64, MVT::i64, Custom); + if (!Subtarget->is64Bit()) { + setOperationAction(ISD::ATOMIC_LOAD_ADD_64, MVT::i64, Custom); + setOperationAction(ISD::ATOMIC_LOAD_SUB_64, MVT::i64, Custom); + setOperationAction(ISD::ATOMIC_LOAD_AND_64, MVT::i64, Custom); + setOperationAction(ISD::ATOMIC_LOAD_OR_64, MVT::i64, Custom); + setOperationAction(ISD::ATOMIC_LOAD_XOR_64, MVT::i64, Custom); + setOperationAction(ISD::ATOMIC_LOAD_NAND_64, MVT::i64, Custom); + setOperationAction(ISD::ATOMIC_SWAP_64, MVT::i64, Custom); + } + // Use the default ISD::DBG_STOPPOINT, ISD::DECLARE expansion. setOperationAction(ISD::DBG_STOPPOINT, MVT::Other, Expand); // FIXME - use subtarget debug flags @@ -6004,6 +6014,27 @@ SDNode* X86TargetLowering::ExpandATOMIC_CMP_SWAP(SDNode* Op, return DAG.getMergeValues(Vals, 2).getNode(); } +SDValue X86TargetLowering::LowerATOMIC_BINARY_64(SDValue Op, + SelectionDAG &DAG, + unsigned NewOp) { + SDNode *Node = Op.getNode(); + MVT T = Node->getValueType(0); + assert (T == MVT::i64 && "Only know how to expand i64 atomics"); + + SDValue Chain = Node->getOperand(0); + SDValue In1 = Node->getOperand(1); + assert(Node->getOperand(2).getNode()->getOpcode()==ISD::BUILD_PAIR); + SDValue In2L = Node->getOperand(2).getNode()->getOperand(0); + SDValue In2H = Node->getOperand(2).getNode()->getOperand(1); + SDValue Ops[] = { Chain, In1, In2L, In2H }; + SDVTList Tys = DAG.getVTList(MVT::i32, MVT::i32, MVT::Other); + SDValue Result = DAG.getNode(NewOp, Tys, Ops, 4); + SDValue OpsF[] = { Result.getValue(0), Result.getValue(1)}; + SDValue ResultVal = DAG.getNode(ISD::BUILD_PAIR, MVT::i64, OpsF, 2); + SDValue Vals[2] = { ResultVal, Result.getValue(2) }; + return SDValue(DAG.getMergeValues(Vals, 2).getNode(), 0); +} + SDValue X86TargetLowering::LowerLOAD_SUB(SDValue Op, SelectionDAG &DAG) { SDNode *Node = Op.getNode(); MVT T = Node->getValueType(0); @@ -6027,14 +6058,27 @@ SDValue X86TargetLowering::LowerLOAD_SUB(SDValue Op, SelectionDAG &DAG) { SDValue X86TargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) { switch (Op.getOpcode()) { default: assert(0 && "Should not custom lower this!"); - case ISD::ATOMIC_CMP_SWAP_8: return LowerCMP_SWAP(Op,DAG); - case ISD::ATOMIC_CMP_SWAP_16: return LowerCMP_SWAP(Op,DAG); - case ISD::ATOMIC_CMP_SWAP_32: return LowerCMP_SWAP(Op,DAG); + case ISD::ATOMIC_CMP_SWAP_8: + case ISD::ATOMIC_CMP_SWAP_16: + case ISD::ATOMIC_CMP_SWAP_32: case ISD::ATOMIC_CMP_SWAP_64: return LowerCMP_SWAP(Op,DAG); - case ISD::ATOMIC_LOAD_SUB_8: return LowerLOAD_SUB(Op,DAG); - case ISD::ATOMIC_LOAD_SUB_16: return LowerLOAD_SUB(Op,DAG); + case ISD::ATOMIC_LOAD_SUB_8: + case ISD::ATOMIC_LOAD_SUB_16: case ISD::ATOMIC_LOAD_SUB_32: return LowerLOAD_SUB(Op,DAG); - case ISD::ATOMIC_LOAD_SUB_64: return LowerLOAD_SUB(Op,DAG); + case ISD::ATOMIC_LOAD_SUB_64: return (Subtarget->is64Bit()) ? + LowerLOAD_SUB(Op,DAG) : + LowerATOMIC_BINARY_64(Op,DAG, + X86ISD::ATOMSUB64_DAG); + case ISD::ATOMIC_LOAD_AND_64: return LowerATOMIC_BINARY_64(Op,DAG, + X86ISD::ATOMAND64_DAG); + case ISD::ATOMIC_LOAD_OR_64: return LowerATOMIC_BINARY_64(Op, DAG, + X86ISD::ATOMOR64_DAG); + case ISD::ATOMIC_LOAD_XOR_64: return LowerATOMIC_BINARY_64(Op,DAG, + X86ISD::ATOMXOR64_DAG); + case ISD::ATOMIC_LOAD_NAND_64: return LowerATOMIC_BINARY_64(Op,DAG, + X86ISD::ATOMNAND64_DAG); + case ISD::ATOMIC_LOAD_ADD_64: return LowerATOMIC_BINARY_64(Op,DAG, + X86ISD::ATOMADD64_DAG); case ISD::BUILD_VECTOR: return LowerBUILD_VECTOR(Op, DAG); case ISD::VECTOR_SHUFFLE: return LowerVECTOR_SHUFFLE(Op, DAG); case ISD::EXTRACT_VECTOR_ELT: return LowerEXTRACT_VECTOR_ELT(Op, DAG); @@ -6140,6 +6184,12 @@ const char *X86TargetLowering::getTargetNodeName(unsigned Opcode) const { case X86ISD::FNSTCW16m: return "X86ISD::FNSTCW16m"; case X86ISD::LCMPXCHG_DAG: return "X86ISD::LCMPXCHG_DAG"; case X86ISD::LCMPXCHG8_DAG: return "X86ISD::LCMPXCHG8_DAG"; + case X86ISD::ATOMADD64_DAG: return "X86ISD::ATOMADD64_DAG"; + case X86ISD::ATOMSUB64_DAG: return "X86ISD::ATOMSUB64_DAG"; + case X86ISD::ATOMOR64_DAG: return "X86ISD::ATOMOR64_DAG"; + case X86ISD::ATOMXOR64_DAG: return "X86ISD::ATOMXOR64_DAG"; + case X86ISD::ATOMAND64_DAG: return "X86ISD::ATOMAND64_DAG"; + case X86ISD::ATOMNAND64_DAG: return "X86ISD::ATOMNAND64_DAG"; case X86ISD::VZEXT_MOVL: return "X86ISD::VZEXT_MOVL"; case X86ISD::VZEXT_LOAD: return "X86ISD::VZEXT_LOAD"; case X86ISD::VSHL: return "X86ISD::VSHL"; @@ -6365,6 +6415,146 @@ X86TargetLowering::EmitAtomicBitwiseWithCustomInserter(MachineInstr *bInstr, return nextMBB; } +// private utility function +MachineBasicBlock * +X86TargetLowering::EmitAtomicBit6432WithCustomInserter(MachineInstr *bInstr, + MachineBasicBlock *MBB, + unsigned regOpcL, + unsigned regOpcH, + unsigned immOpcL, + unsigned immOpcH, + bool invSrc) { + // For the atomic bitwise operator, we generate + // thisMBB (instructions are in pairs, except cmpxchg8b) + // ld t1,t2 = [bitinstr.addr] + // newMBB: + // out1, out2 = phi (thisMBB, t1/t2) (newMBB, t3/t4) + // op t5, t6 <- out1, out2, [bitinstr.val] + // mov ECX, EBX <- t5, t6 + // mov EAX, EDX <- t1, t2 + // cmpxchg8b [bitinstr.addr] [EAX, EDX, EBX, ECX implicit] + // mov t3, t4 <- EAX, EDX + // bz newMBB + // result in out1, out2 + // fallthrough -->nextMBB + + const TargetRegisterClass *RC = X86::GR32RegisterClass; + const unsigned LoadOpc = X86::MOV32rm; + const unsigned copyOpc = X86::MOV32rr; + const unsigned NotOpc = X86::NOT32r; + const TargetInstrInfo *TII = getTargetMachine().getInstrInfo(); + const BasicBlock *LLVM_BB = MBB->getBasicBlock(); + MachineFunction::iterator MBBIter = MBB; + ++MBBIter; + + /// First build the CFG + MachineFunction *F = MBB->getParent(); + MachineBasicBlock *thisMBB = MBB; + MachineBasicBlock *newMBB = F->CreateMachineBasicBlock(LLVM_BB); + MachineBasicBlock *nextMBB = F->CreateMachineBasicBlock(LLVM_BB); + F->insert(MBBIter, newMBB); + F->insert(MBBIter, nextMBB); + + // Move all successors to thisMBB to nextMBB + nextMBB->transferSuccessors(thisMBB); + + // Update thisMBB to fall through to newMBB + thisMBB->addSuccessor(newMBB); + + // newMBB jumps to itself and fall through to nextMBB + newMBB->addSuccessor(nextMBB); + newMBB->addSuccessor(newMBB); + + // Insert instructions into newMBB based on incoming instruction + // There are 8 "real" operands plus 9 implicit def/uses, ignored here. + assert(bInstr->getNumOperands() < 18 && "unexpected number of operands"); + MachineOperand& dest1Oper = bInstr->getOperand(0); + MachineOperand& dest2Oper = bInstr->getOperand(1); + MachineOperand* argOpers[6]; + for (int i=0; i < 6; ++i) + argOpers[i] = &bInstr->getOperand(i+2); + + // x86 address has 4 operands: base, index, scale, and displacement + int lastAddrIndx = 3; // [0,3] + + unsigned t1 = F->getRegInfo().createVirtualRegister(RC); + MachineInstrBuilder MIB = BuildMI(thisMBB, TII->get(LoadOpc), t1); + for (int i=0; i <= lastAddrIndx; ++i) + (*MIB).addOperand(*argOpers[i]); + unsigned t2 = F->getRegInfo().createVirtualRegister(RC); + MIB = BuildMI(thisMBB, TII->get(LoadOpc), t2); + // add 4 to displacement. getImm verifies it's immediate. + for (int i=0; i <= lastAddrIndx-1; ++i) + (*MIB).addOperand(*argOpers[i]); + MachineOperand newOp3 = MachineOperand::CreateImm(argOpers[3]->getImm()+4); + (*MIB).addOperand(newOp3); + + // t3/4 are defined later, at the bottom of the loop + unsigned t3 = F->getRegInfo().createVirtualRegister(RC); + unsigned t4 = F->getRegInfo().createVirtualRegister(RC); + BuildMI(newMBB, TII->get(X86::PHI), dest1Oper.getReg()) + .addReg(t1).addMBB(thisMBB).addReg(t3).addMBB(newMBB); + BuildMI(newMBB, TII->get(X86::PHI), dest2Oper.getReg()) + .addReg(t2).addMBB(thisMBB).addReg(t4).addMBB(newMBB); + + unsigned tt1 = F->getRegInfo().createVirtualRegister(RC); + unsigned tt2 = F->getRegInfo().createVirtualRegister(RC); + if (invSrc) { + MIB = BuildMI(newMBB, TII->get(NotOpc), tt1).addReg(t1); + MIB = BuildMI(newMBB, TII->get(NotOpc), tt2).addReg(t2); + } else { + tt1 = t1; + tt2 = t2; + } + + assert((argOpers[4]->isRegister() || argOpers[4]->isImmediate()) && + "invalid operand"); + unsigned t5 = F->getRegInfo().createVirtualRegister(RC); + unsigned t6 = F->getRegInfo().createVirtualRegister(RC); + if (argOpers[4]->isRegister()) + MIB = BuildMI(newMBB, TII->get(regOpcL), t5); + else + MIB = BuildMI(newMBB, TII->get(immOpcL), t5); + MIB.addReg(tt1); + (*MIB).addOperand(*argOpers[4]); + assert(argOpers[5]->isRegister() == argOpers[4]->isRegister()); + assert(argOpers[5]->isImmediate() == argOpers[4]->isImmediate()); + if (argOpers[5]->isRegister()) + MIB = BuildMI(newMBB, TII->get(regOpcH), t6); + else + MIB = BuildMI(newMBB, TII->get(immOpcH), t6); + MIB.addReg(tt2); + (*MIB).addOperand(*argOpers[5]); + + MIB = BuildMI(newMBB, TII->get(copyOpc), X86::EAX); + MIB.addReg(t1); + MIB = BuildMI(newMBB, TII->get(copyOpc), X86::EDX); + MIB.addReg(t2); + + MIB = BuildMI(newMBB, TII->get(copyOpc), X86::EBX); + MIB.addReg(t5); + MIB = BuildMI(newMBB, TII->get(copyOpc), X86::ECX); + MIB.addReg(t6); + + MIB = BuildMI(newMBB, TII->get(X86::LCMPXCHG8B)); + for (int i=0; i <= lastAddrIndx; ++i) + (*MIB).addOperand(*argOpers[i]); + + assert(bInstr->hasOneMemOperand() && "Unexpected number of memoperand"); + (*MIB).addMemOperand(*F, *bInstr->memoperands_begin()); + + MIB = BuildMI(newMBB, TII->get(copyOpc), t3); + MIB.addReg(X86::EAX); + MIB = BuildMI(newMBB, TII->get(copyOpc), t4); + MIB.addReg(X86::EDX); + + // insert branch + BuildMI(newMBB, TII->get(X86::JNE)).addMBB(newMBB); + + F->DeleteMachineInstr(bInstr); // The pseudo instruction is gone now. + return nextMBB; +} + // private utility function MachineBasicBlock * X86TargetLowering::EmitAtomicMinMaxWithCustomInserter(MachineInstr *mInstr, @@ -6695,6 +6885,7 @@ X86TargetLowering::EmitInstrWithCustomInserter(MachineInstr *MI, X86::NOT8r, X86::AL, X86::GR8RegisterClass, true); // FIXME: There are no CMOV8 instructions; MIN/MAX need some other way. + // This group is for 64-bit host. case X86::ATOMAND64: return EmitAtomicBitwiseWithCustomInserter(MI, BB, X86::AND64rr, X86::AND64ri32, X86::MOV64rm, @@ -6727,6 +6918,40 @@ X86TargetLowering::EmitInstrWithCustomInserter(MachineInstr *MI, return EmitAtomicMinMaxWithCustomInserter(MI, BB, X86::CMOVB64rr); case X86::ATOMUMAX64: return EmitAtomicMinMaxWithCustomInserter(MI, BB, X86::CMOVA64rr); + + // This group does 64-bit operations on a 32-bit host. + case X86::ATOMAND6432: + return EmitAtomicBit6432WithCustomInserter(MI, BB, + X86::AND32rr, X86::AND32rr, + X86::AND32ri, X86::AND32ri, + false); + case X86::ATOMOR6432: + return EmitAtomicBit6432WithCustomInserter(MI, BB, + X86::OR32rr, X86::OR32rr, + X86::OR32ri, X86::OR32ri, + false); + case X86::ATOMXOR6432: + return EmitAtomicBit6432WithCustomInserter(MI, BB, + X86::XOR32rr, X86::XOR32rr, + X86::XOR32ri, X86::XOR32ri, + false); + case X86::ATOMNAND6432: + return EmitAtomicBit6432WithCustomInserter(MI, BB, + X86::AND32rr, X86::AND32rr, + X86::AND32ri, X86::AND32ri, + true); + // FIXME carry + case X86::ATOMADD6432: + return EmitAtomicBit6432WithCustomInserter(MI, BB, + X86::ADD32rr, X86::ADC32rr, + X86::ADD32ri, X86::ADC32ri, + false); + // FIXME carry + case X86::ATOMSUB6432: + return EmitAtomicBit6432WithCustomInserter(MI, BB, + X86::SUB32rr, X86::SBB32rr, + X86::SUB32ri, X86::SBB32ri, + false); } } diff --git a/llvm/lib/Target/X86/X86ISelLowering.h b/llvm/lib/Target/X86/X86ISelLowering.h index 54a74533eb3a..f12ff7070334 100644 --- a/llvm/lib/Target/X86/X86ISelLowering.h +++ b/llvm/lib/Target/X86/X86ISelLowering.h @@ -199,6 +199,15 @@ namespace llvm { LCMPXCHG_DAG, LCMPXCHG8_DAG, + // ATOMADD64_DAG, ATOMSUB64_DAG, ATOMOR64_DAG, ATOMAND64_DAG, + // ATOMXOR64_DAG, ATOMNAND64_DAG - Atomic 64-bit binary operations. + ATOMADD64_DAG, + ATOMSUB64_DAG, + ATOMOR64_DAG, + ATOMXOR64_DAG, + ATOMAND64_DAG, + ATOMNAND64_DAG, + // FNSTCW16m - Store FP control world into i16 memory. FNSTCW16m, @@ -570,6 +579,8 @@ namespace llvm { SDValue LowerCTTZ(SDValue Op, SelectionDAG &DAG); SDValue LowerCMP_SWAP(SDValue Op, SelectionDAG &DAG); SDValue LowerLOAD_SUB(SDValue Op, SelectionDAG &DAG); + SDValue LowerATOMIC_BINARY_64(SDValue Op, SelectionDAG &DAG, + unsigned NewOp); SDNode *ExpandFP_TO_SINT(SDNode *N, SelectionDAG &DAG); SDNode *ExpandREADCYCLECOUNTER(SDNode *N, SelectionDAG &DAG); SDNode *ExpandATOMIC_CMP_SWAP(SDNode *N, SelectionDAG &DAG); @@ -602,6 +613,15 @@ namespace llvm { unsigned EAXreg, TargetRegisterClass *RC, bool invSrc = false); + + MachineBasicBlock *EmitAtomicBit6432WithCustomInserter( + MachineInstr *BInstr, + MachineBasicBlock *BB, + unsigned regOpcL, + unsigned regOpcH, + unsigned immOpcL, + unsigned immOpcH, + bool invSrc = false); /// Utility function to emit atomic min and max. It takes the min/max // instruction to expand, the associated basic block, and the associated diff --git a/llvm/lib/Target/X86/X86InstrInfo.td b/llvm/lib/Target/X86/X86InstrInfo.td index 6ffff6bad263..de80bb2d45b8 100644 --- a/llvm/lib/Target/X86/X86InstrInfo.td +++ b/llvm/lib/Target/X86/X86InstrInfo.td @@ -39,6 +39,8 @@ def SDTX86cas : SDTypeProfile<0, 3, [SDTCisPtrTy<0>, SDTCisInt<1>, SDTCisVT<2, i8>]>; def SDTX86cas8 : SDTypeProfile<0, 1, [SDTCisPtrTy<0>]>; +def SDTX86atomicBinary : SDTypeProfile<2, 3, [SDTCisInt<0>, SDTCisInt<1>, + SDTCisPtrTy<2>, SDTCisInt<3>,SDTCisInt<4>]>; def SDTX86Ret : SDTypeProfile<0, -1, [SDTCisVT<0, i16>]>; def SDT_X86CallSeqStart : SDCallSeqStart<[ SDTCisVT<0, i32> ]>; @@ -79,7 +81,24 @@ def X86cas : SDNode<"X86ISD::LCMPXCHG_DAG", SDTX86cas, def X86cas8 : SDNode<"X86ISD::LCMPXCHG8_DAG", SDTX86cas8, [SDNPHasChain, SDNPInFlag, SDNPOutFlag, SDNPMayStore, SDNPMayLoad]>; - +def X86AtomAdd64 : SDNode<"X86ISD::ATOMADD64_DAG", SDTX86atomicBinary, + [SDNPHasChain, SDNPMayStore, + SDNPMayLoad, SDNPMemOperand]>; +def X86AtomSub64 : SDNode<"X86ISD::ATOMSUB64_DAG", SDTX86atomicBinary, + [SDNPHasChain, SDNPMayStore, + SDNPMayLoad, SDNPMemOperand]>; +def X86AtomOr64 : SDNode<"X86ISD::ATOMOR64_DAG", SDTX86atomicBinary, + [SDNPHasChain, SDNPMayStore, + SDNPMayLoad, SDNPMemOperand]>; +def X86AtomXor64 : SDNode<"X86ISD::ATOMXOR64_DAG", SDTX86atomicBinary, + [SDNPHasChain, SDNPMayStore, + SDNPMayLoad, SDNPMemOperand]>; +def X86AtomAnd64 : SDNode<"X86ISD::ATOMAND64_DAG", SDTX86atomicBinary, + [SDNPHasChain, SDNPMayStore, + SDNPMayLoad, SDNPMemOperand]>; +def X86AtomNand64 : SDNode<"X86ISD::ATOMNAND64_DAG", SDTX86atomicBinary, + [SDNPHasChain, SDNPMayStore, + SDNPMayLoad, SDNPMemOperand]>; def X86retflag : SDNode<"X86ISD::RET_FLAG", SDTX86Ret, [SDNPHasChain, SDNPOptInFlag]>; @@ -2630,7 +2649,7 @@ def LCMPXCHG32 : I<0xB1, MRMDestMem, (outs), (ins i32mem:$ptr, GR32:$swap), "lock\n\tcmpxchg{l}\t{$swap, $ptr|$ptr, $swap}", [(X86cas addr:$ptr, GR32:$swap, 4)]>, TB, LOCK; } -let Defs = [EAX, EBX, ECX, EDX, EFLAGS], Uses = [EAX, EBX, ECX, EDX] in { +let Defs = [EAX, EDX, EFLAGS], Uses = [EAX, EBX, ECX, EDX] in { def LCMPXCHG8B : I<0xC7, MRM1m, (outs), (ins i32mem:$ptr), "lock\n\tcmpxchg8b\t$ptr", [(X86cas8 addr:$ptr)]>, TB, LOCK; @@ -2730,6 +2749,30 @@ def ATOMNAND8 : I<0, Pseudo,(outs GR8:$dst),(ins i8mem:$ptr, GR8:$val), [(set GR8:$dst, (atomic_load_nand_8 addr:$ptr, GR8:$val))]>; } +let Constraints = "$val1 = $dst1, $val2 = $dst2", + Defs = [EFLAGS, EAX, EBX, ECX, EDX], + Uses = [EAX, EBX, ECX, EDX], + usesCustomDAGSchedInserter = 1 in { +def ATOMAND6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2), + (ins i64mem:$ptr, GR32:$val1, GR32:$val2), + "#ATOMAND6432 PSUEDO!", []>; +def ATOMOR6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2), + (ins i64mem:$ptr, GR32:$val1, GR32:$val2), + "#ATOMOR6432 PSUEDO!", []>; +def ATOMXOR6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2), + (ins i64mem:$ptr, GR32:$val1, GR32:$val2), + "#ATOMXOR6432 PSUEDO!", []>; +def ATOMNAND6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2), + (ins i64mem:$ptr, GR32:$val1, GR32:$val2), + "#ATOMNAND6432 PSUEDO!", []>; +def ATOMADD6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2), + (ins i64mem:$ptr, GR32:$val1, GR32:$val2), + "#ATOMADD6432 PSUEDO!", []>; +def ATOMSUB6432 : I<0, Pseudo, (outs GR32:$dst1, GR32:$dst2), + (ins i64mem:$ptr, GR32:$val1, GR32:$val2), + "#ATOMSUB6432 PSUEDO!", []>; +} + //===----------------------------------------------------------------------===// // Non-Instruction Patterns //===----------------------------------------------------------------------===// diff --git a/llvm/test/CodeGen/X86/2008-10-02-Atomics32-2.ll b/llvm/test/CodeGen/X86/2008-10-02-Atomics32-2.ll new file mode 100644 index 000000000000..3cf9deea6e49 --- /dev/null +++ b/llvm/test/CodeGen/X86/2008-10-02-Atomics32-2.ll @@ -0,0 +1,969 @@ +; RUN: llvm-as < %s | llc -march=x86 +;; This version includes 64-bit version of binary operators (in 32-bit mode). +;; Swap, cmp-and-swap not supported yet in this mode. +; ModuleID = 'Atomics.c' +target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128" +target triple = "i386-apple-darwin8" +@sc = common global i8 0 ; [#uses=52] +@uc = common global i8 0 ; [#uses=112] +@ss = common global i16 0 ; [#uses=15] +@us = common global i16 0 ; [#uses=15] +@si = common global i32 0 ; [#uses=15] +@ui = common global i32 0 ; [#uses=23] +@sl = common global i32 0 ; [#uses=15] +@ul = common global i32 0 ; [#uses=15] +@sll = common global i64 0, align 8 ; [#uses=13] +@ull = common global i64 0, align 8 ; [#uses=13] + +define void @test_op_ignore() nounwind { +entry: + %0 = call i8 @llvm.atomic.load.add.i8.p0i8(i8* @sc, i8 1) ; [#uses=0] + %1 = call i8 @llvm.atomic.load.add.i8.p0i8(i8* @uc, i8 1) ; [#uses=0] + %2 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %3 = call i16 @llvm.atomic.load.add.i16.p0i16(i16* %2, i16 1) ; [#uses=0] + %4 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %5 = call i16 @llvm.atomic.load.add.i16.p0i16(i16* %4, i16 1) ; [#uses=0] + %6 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %7 = call i32 @llvm.atomic.load.add.i32.p0i32(i32* %6, i32 1) ; [#uses=0] + %8 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %9 = call i32 @llvm.atomic.load.add.i32.p0i32(i32* %8, i32 1) ; [#uses=0] + %10 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %11 = call i32 @llvm.atomic.load.add.i32.p0i32(i32* %10, i32 1) ; [#uses=0] + %12 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %13 = call i32 @llvm.atomic.load.add.i32.p0i32(i32* %12, i32 1) ; [#uses=0] + %14 = bitcast i8* bitcast (i64* @sll to i8*) to i64* ; [#uses=1] + %15 = call i64 @llvm.atomic.load.add.i64.p0i64(i64* %14, i64 1) ; [#uses=0] + %16 = bitcast i8* bitcast (i64* @ull to i8*) to i64* ; [#uses=1] + %17 = call i64 @llvm.atomic.load.add.i64.p0i64(i64* %16, i64 1) ; [#uses=0] + %18 = call i8 @llvm.atomic.load.sub.i8.p0i8(i8* @sc, i8 1) ; [#uses=0] + %19 = call i8 @llvm.atomic.load.sub.i8.p0i8(i8* @uc, i8 1) ; [#uses=0] + %20 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %21 = call i16 @llvm.atomic.load.sub.i16.p0i16(i16* %20, i16 1) ; [#uses=0] + %22 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %23 = call i16 @llvm.atomic.load.sub.i16.p0i16(i16* %22, i16 1) ; [#uses=0] + %24 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %25 = call i32 @llvm.atomic.load.sub.i32.p0i32(i32* %24, i32 1) ; [#uses=0] + %26 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %27 = call i32 @llvm.atomic.load.sub.i32.p0i32(i32* %26, i32 1) ; [#uses=0] + %28 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %29 = call i32 @llvm.atomic.load.sub.i32.p0i32(i32* %28, i32 1) ; [#uses=0] + %30 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %31 = call i32 @llvm.atomic.load.sub.i32.p0i32(i32* %30, i32 1) ; [#uses=0] + %32 = bitcast i8* bitcast (i64* @sll to i8*) to i64* ; [#uses=1] + %33 = call i64 @llvm.atomic.load.sub.i64.p0i64(i64* %32, i64 1) ; [#uses=0] + %34 = bitcast i8* bitcast (i64* @ull to i8*) to i64* ; [#uses=1] + %35 = call i64 @llvm.atomic.load.sub.i64.p0i64(i64* %34, i64 1) ; [#uses=0] + %36 = call i8 @llvm.atomic.load.or.i8.p0i8(i8* @sc, i8 1) ; [#uses=0] + %37 = call i8 @llvm.atomic.load.or.i8.p0i8(i8* @uc, i8 1) ; [#uses=0] + %38 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %39 = call i16 @llvm.atomic.load.or.i16.p0i16(i16* %38, i16 1) ; [#uses=0] + %40 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %41 = call i16 @llvm.atomic.load.or.i16.p0i16(i16* %40, i16 1) ; [#uses=0] + %42 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %43 = call i32 @llvm.atomic.load.or.i32.p0i32(i32* %42, i32 1) ; [#uses=0] + %44 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %45 = call i32 @llvm.atomic.load.or.i32.p0i32(i32* %44, i32 1) ; [#uses=0] + %46 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %47 = call i32 @llvm.atomic.load.or.i32.p0i32(i32* %46, i32 1) ; [#uses=0] + %48 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %49 = call i32 @llvm.atomic.load.or.i32.p0i32(i32* %48, i32 1) ; [#uses=0] + %50 = bitcast i8* bitcast (i64* @sll to i8*) to i64* ; [#uses=1] + %51 = call i64 @llvm.atomic.load.or.i64.p0i64(i64* %50, i64 1) ; [#uses=0] + %52 = bitcast i8* bitcast (i64* @ull to i8*) to i64* ; [#uses=1] + %53 = call i64 @llvm.atomic.load.or.i64.p0i64(i64* %52, i64 1) ; [#uses=0] + %54 = call i8 @llvm.atomic.load.xor.i8.p0i8(i8* @sc, i8 1) ; [#uses=0] + %55 = call i8 @llvm.atomic.load.xor.i8.p0i8(i8* @uc, i8 1) ; [#uses=0] + %56 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %57 = call i16 @llvm.atomic.load.xor.i16.p0i16(i16* %56, i16 1) ; [#uses=0] + %58 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %59 = call i16 @llvm.atomic.load.xor.i16.p0i16(i16* %58, i16 1) ; [#uses=0] + %60 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %61 = call i32 @llvm.atomic.load.xor.i32.p0i32(i32* %60, i32 1) ; [#uses=0] + %62 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %63 = call i32 @llvm.atomic.load.xor.i32.p0i32(i32* %62, i32 1) ; [#uses=0] + %64 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %65 = call i32 @llvm.atomic.load.xor.i32.p0i32(i32* %64, i32 1) ; [#uses=0] + %66 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %67 = call i32 @llvm.atomic.load.xor.i32.p0i32(i32* %66, i32 1) ; [#uses=0] + %68 = bitcast i8* bitcast (i64* @sll to i8*) to i64* ; [#uses=1] + %69 = call i64 @llvm.atomic.load.xor.i64.p0i64(i64* %68, i64 1) ; [#uses=0] + %70 = bitcast i8* bitcast (i64* @ull to i8*) to i64* ; [#uses=1] + %71 = call i64 @llvm.atomic.load.xor.i64.p0i64(i64* %70, i64 1) ; [#uses=0] + %72 = call i8 @llvm.atomic.load.and.i8.p0i8(i8* @sc, i8 1) ; [#uses=0] + %73 = call i8 @llvm.atomic.load.and.i8.p0i8(i8* @uc, i8 1) ; [#uses=0] + %74 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %75 = call i16 @llvm.atomic.load.and.i16.p0i16(i16* %74, i16 1) ; [#uses=0] + %76 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %77 = call i16 @llvm.atomic.load.and.i16.p0i16(i16* %76, i16 1) ; [#uses=0] + %78 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %79 = call i32 @llvm.atomic.load.and.i32.p0i32(i32* %78, i32 1) ; [#uses=0] + %80 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %81 = call i32 @llvm.atomic.load.and.i32.p0i32(i32* %80, i32 1) ; [#uses=0] + %82 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %83 = call i32 @llvm.atomic.load.and.i32.p0i32(i32* %82, i32 1) ; [#uses=0] + %84 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %85 = call i32 @llvm.atomic.load.and.i32.p0i32(i32* %84, i32 1) ; [#uses=0] + %86 = bitcast i8* bitcast (i64* @sll to i8*) to i64* ; [#uses=1] + %87 = call i64 @llvm.atomic.load.and.i64.p0i64(i64* %86, i64 1) ; [#uses=0] + %88 = bitcast i8* bitcast (i64* @ull to i8*) to i64* ; [#uses=1] + %89 = call i64 @llvm.atomic.load.and.i64.p0i64(i64* %88, i64 1) ; [#uses=0] + %90 = call i8 @llvm.atomic.load.nand.i8.p0i8(i8* @sc, i8 1) ; [#uses=0] + %91 = call i8 @llvm.atomic.load.nand.i8.p0i8(i8* @uc, i8 1) ; [#uses=0] + %92 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %93 = call i16 @llvm.atomic.load.nand.i16.p0i16(i16* %92, i16 1) ; [#uses=0] + %94 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %95 = call i16 @llvm.atomic.load.nand.i16.p0i16(i16* %94, i16 1) ; [#uses=0] + %96 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %97 = call i32 @llvm.atomic.load.nand.i32.p0i32(i32* %96, i32 1) ; [#uses=0] + %98 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %99 = call i32 @llvm.atomic.load.nand.i32.p0i32(i32* %98, i32 1) ; [#uses=0] + %100 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %101 = call i32 @llvm.atomic.load.nand.i32.p0i32(i32* %100, i32 1) ; [#uses=0] + %102 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %103 = call i32 @llvm.atomic.load.nand.i32.p0i32(i32* %102, i32 1) ; [#uses=0] + %104 = bitcast i8* bitcast (i64* @sll to i8*) to i64* ; [#uses=1] + %105 = call i64 @llvm.atomic.load.nand.i64.p0i64(i64* %104, i64 1) ; [#uses=0] + %106 = bitcast i8* bitcast (i64* @ull to i8*) to i64* ; [#uses=1] + %107 = call i64 @llvm.atomic.load.nand.i64.p0i64(i64* %106, i64 1) ; [#uses=0] + br label %return + +return: ; preds = %entry + ret void +} + +declare i8 @llvm.atomic.load.add.i8.p0i8(i8*, i8) nounwind + +declare i16 @llvm.atomic.load.add.i16.p0i16(i16*, i16) nounwind + +declare i32 @llvm.atomic.load.add.i32.p0i32(i32*, i32) nounwind + +declare i64 @llvm.atomic.load.add.i64.p0i64(i64*, i64) nounwind + +declare i8 @llvm.atomic.load.sub.i8.p0i8(i8*, i8) nounwind + +declare i16 @llvm.atomic.load.sub.i16.p0i16(i16*, i16) nounwind + +declare i32 @llvm.atomic.load.sub.i32.p0i32(i32*, i32) nounwind + +declare i64 @llvm.atomic.load.sub.i64.p0i64(i64*, i64) nounwind + +declare i8 @llvm.atomic.load.or.i8.p0i8(i8*, i8) nounwind + +declare i16 @llvm.atomic.load.or.i16.p0i16(i16*, i16) nounwind + +declare i32 @llvm.atomic.load.or.i32.p0i32(i32*, i32) nounwind + +declare i64 @llvm.atomic.load.or.i64.p0i64(i64*, i64) nounwind + +declare i8 @llvm.atomic.load.xor.i8.p0i8(i8*, i8) nounwind + +declare i16 @llvm.atomic.load.xor.i16.p0i16(i16*, i16) nounwind + +declare i32 @llvm.atomic.load.xor.i32.p0i32(i32*, i32) nounwind + +declare i64 @llvm.atomic.load.xor.i64.p0i64(i64*, i64) nounwind + +declare i8 @llvm.atomic.load.and.i8.p0i8(i8*, i8) nounwind + +declare i16 @llvm.atomic.load.and.i16.p0i16(i16*, i16) nounwind + +declare i32 @llvm.atomic.load.and.i32.p0i32(i32*, i32) nounwind + +declare i64 @llvm.atomic.load.and.i64.p0i64(i64*, i64) nounwind + +declare i8 @llvm.atomic.load.nand.i8.p0i8(i8*, i8) nounwind + +declare i16 @llvm.atomic.load.nand.i16.p0i16(i16*, i16) nounwind + +declare i32 @llvm.atomic.load.nand.i32.p0i32(i32*, i32) nounwind + +declare i64 @llvm.atomic.load.nand.i64.p0i64(i64*, i64) nounwind + +define void @test_fetch_and_op() nounwind { +entry: + %0 = call i8 @llvm.atomic.load.add.i8.p0i8(i8* @sc, i8 11) ; [#uses=1] + store i8 %0, i8* @sc, align 1 + %1 = call i8 @llvm.atomic.load.add.i8.p0i8(i8* @uc, i8 11) ; [#uses=1] + store i8 %1, i8* @uc, align 1 + %2 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %3 = call i16 @llvm.atomic.load.add.i16.p0i16(i16* %2, i16 11) ; [#uses=1] + store i16 %3, i16* @ss, align 2 + %4 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %5 = call i16 @llvm.atomic.load.add.i16.p0i16(i16* %4, i16 11) ; [#uses=1] + store i16 %5, i16* @us, align 2 + %6 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %7 = call i32 @llvm.atomic.load.add.i32.p0i32(i32* %6, i32 11) ; [#uses=1] + store i32 %7, i32* @si, align 4 + %8 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %9 = call i32 @llvm.atomic.load.add.i32.p0i32(i32* %8, i32 11) ; [#uses=1] + store i32 %9, i32* @ui, align 4 + %10 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %11 = call i32 @llvm.atomic.load.add.i32.p0i32(i32* %10, i32 11) ; [#uses=1] + store i32 %11, i32* @sl, align 4 + %12 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %13 = call i32 @llvm.atomic.load.add.i32.p0i32(i32* %12, i32 11) ; [#uses=1] + store i32 %13, i32* @ul, align 4 + %14 = bitcast i8* bitcast (i64* @sll to i8*) to i64* ; [#uses=1] + %15 = call i64 @llvm.atomic.load.add.i64.p0i64(i64* %14, i64 11) ; [#uses=1] + store i64 %15, i64* @sll, align 8 + %16 = bitcast i8* bitcast (i64* @ull to i8*) to i64* ; [#uses=1] + %17 = call i64 @llvm.atomic.load.add.i64.p0i64(i64* %16, i64 11) ; [#uses=1] + store i64 %17, i64* @ull, align 8 + %18 = call i8 @llvm.atomic.load.sub.i8.p0i8(i8* @sc, i8 11) ; [#uses=1] + store i8 %18, i8* @sc, align 1 + %19 = call i8 @llvm.atomic.load.sub.i8.p0i8(i8* @uc, i8 11) ; [#uses=1] + store i8 %19, i8* @uc, align 1 + %20 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %21 = call i16 @llvm.atomic.load.sub.i16.p0i16(i16* %20, i16 11) ; [#uses=1] + store i16 %21, i16* @ss, align 2 + %22 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %23 = call i16 @llvm.atomic.load.sub.i16.p0i16(i16* %22, i16 11) ; [#uses=1] + store i16 %23, i16* @us, align 2 + %24 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %25 = call i32 @llvm.atomic.load.sub.i32.p0i32(i32* %24, i32 11) ; [#uses=1] + store i32 %25, i32* @si, align 4 + %26 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %27 = call i32 @llvm.atomic.load.sub.i32.p0i32(i32* %26, i32 11) ; [#uses=1] + store i32 %27, i32* @ui, align 4 + %28 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %29 = call i32 @llvm.atomic.load.sub.i32.p0i32(i32* %28, i32 11) ; [#uses=1] + store i32 %29, i32* @sl, align 4 + %30 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %31 = call i32 @llvm.atomic.load.sub.i32.p0i32(i32* %30, i32 11) ; [#uses=1] + store i32 %31, i32* @ul, align 4 + %32 = bitcast i8* bitcast (i64* @sll to i8*) to i64* ; [#uses=1] + %33 = call i64 @llvm.atomic.load.sub.i64.p0i64(i64* %32, i64 11) ; [#uses=1] + store i64 %33, i64* @sll, align 8 + %34 = bitcast i8* bitcast (i64* @ull to i8*) to i64* ; [#uses=1] + %35 = call i64 @llvm.atomic.load.sub.i64.p0i64(i64* %34, i64 11) ; [#uses=1] + store i64 %35, i64* @ull, align 8 + %36 = call i8 @llvm.atomic.load.or.i8.p0i8(i8* @sc, i8 11) ; [#uses=1] + store i8 %36, i8* @sc, align 1 + %37 = call i8 @llvm.atomic.load.or.i8.p0i8(i8* @uc, i8 11) ; [#uses=1] + store i8 %37, i8* @uc, align 1 + %38 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %39 = call i16 @llvm.atomic.load.or.i16.p0i16(i16* %38, i16 11) ; [#uses=1] + store i16 %39, i16* @ss, align 2 + %40 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %41 = call i16 @llvm.atomic.load.or.i16.p0i16(i16* %40, i16 11) ; [#uses=1] + store i16 %41, i16* @us, align 2 + %42 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %43 = call i32 @llvm.atomic.load.or.i32.p0i32(i32* %42, i32 11) ; [#uses=1] + store i32 %43, i32* @si, align 4 + %44 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %45 = call i32 @llvm.atomic.load.or.i32.p0i32(i32* %44, i32 11) ; [#uses=1] + store i32 %45, i32* @ui, align 4 + %46 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %47 = call i32 @llvm.atomic.load.or.i32.p0i32(i32* %46, i32 11) ; [#uses=1] + store i32 %47, i32* @sl, align 4 + %48 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %49 = call i32 @llvm.atomic.load.or.i32.p0i32(i32* %48, i32 11) ; [#uses=1] + store i32 %49, i32* @ul, align 4 + %50 = bitcast i8* bitcast (i64* @sll to i8*) to i64* ; [#uses=1] + %51 = call i64 @llvm.atomic.load.or.i64.p0i64(i64* %50, i64 11) ; [#uses=1] + store i64 %51, i64* @sll, align 8 + %52 = bitcast i8* bitcast (i64* @ull to i8*) to i64* ; [#uses=1] + %53 = call i64 @llvm.atomic.load.or.i64.p0i64(i64* %52, i64 11) ; [#uses=1] + store i64 %53, i64* @ull, align 8 + %54 = call i8 @llvm.atomic.load.xor.i8.p0i8(i8* @sc, i8 11) ; [#uses=1] + store i8 %54, i8* @sc, align 1 + %55 = call i8 @llvm.atomic.load.xor.i8.p0i8(i8* @uc, i8 11) ; [#uses=1] + store i8 %55, i8* @uc, align 1 + %56 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %57 = call i16 @llvm.atomic.load.xor.i16.p0i16(i16* %56, i16 11) ; [#uses=1] + store i16 %57, i16* @ss, align 2 + %58 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %59 = call i16 @llvm.atomic.load.xor.i16.p0i16(i16* %58, i16 11) ; [#uses=1] + store i16 %59, i16* @us, align 2 + %60 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %61 = call i32 @llvm.atomic.load.xor.i32.p0i32(i32* %60, i32 11) ; [#uses=1] + store i32 %61, i32* @si, align 4 + %62 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %63 = call i32 @llvm.atomic.load.xor.i32.p0i32(i32* %62, i32 11) ; [#uses=1] + store i32 %63, i32* @ui, align 4 + %64 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %65 = call i32 @llvm.atomic.load.xor.i32.p0i32(i32* %64, i32 11) ; [#uses=1] + store i32 %65, i32* @sl, align 4 + %66 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %67 = call i32 @llvm.atomic.load.xor.i32.p0i32(i32* %66, i32 11) ; [#uses=1] + store i32 %67, i32* @ul, align 4 + %68 = bitcast i8* bitcast (i64* @sll to i8*) to i64* ; [#uses=1] + %69 = call i64 @llvm.atomic.load.xor.i64.p0i64(i64* %68, i64 11) ; [#uses=1] + store i64 %69, i64* @sll, align 8 + %70 = bitcast i8* bitcast (i64* @ull to i8*) to i64* ; [#uses=1] + %71 = call i64 @llvm.atomic.load.xor.i64.p0i64(i64* %70, i64 11) ; [#uses=1] + store i64 %71, i64* @ull, align 8 + %72 = call i8 @llvm.atomic.load.and.i8.p0i8(i8* @sc, i8 11) ; [#uses=1] + store i8 %72, i8* @sc, align 1 + %73 = call i8 @llvm.atomic.load.and.i8.p0i8(i8* @uc, i8 11) ; [#uses=1] + store i8 %73, i8* @uc, align 1 + %74 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %75 = call i16 @llvm.atomic.load.and.i16.p0i16(i16* %74, i16 11) ; [#uses=1] + store i16 %75, i16* @ss, align 2 + %76 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %77 = call i16 @llvm.atomic.load.and.i16.p0i16(i16* %76, i16 11) ; [#uses=1] + store i16 %77, i16* @us, align 2 + %78 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %79 = call i32 @llvm.atomic.load.and.i32.p0i32(i32* %78, i32 11) ; [#uses=1] + store i32 %79, i32* @si, align 4 + %80 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %81 = call i32 @llvm.atomic.load.and.i32.p0i32(i32* %80, i32 11) ; [#uses=1] + store i32 %81, i32* @ui, align 4 + %82 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %83 = call i32 @llvm.atomic.load.and.i32.p0i32(i32* %82, i32 11) ; [#uses=1] + store i32 %83, i32* @sl, align 4 + %84 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %85 = call i32 @llvm.atomic.load.and.i32.p0i32(i32* %84, i32 11) ; [#uses=1] + store i32 %85, i32* @ul, align 4 + %86 = bitcast i8* bitcast (i64* @sll to i8*) to i64* ; [#uses=1] + %87 = call i64 @llvm.atomic.load.and.i64.p0i64(i64* %86, i64 11) ; [#uses=1] + store i64 %87, i64* @sll, align 8 + %88 = bitcast i8* bitcast (i64* @ull to i8*) to i64* ; [#uses=1] + %89 = call i64 @llvm.atomic.load.and.i64.p0i64(i64* %88, i64 11) ; [#uses=1] + store i64 %89, i64* @ull, align 8 + %90 = call i8 @llvm.atomic.load.nand.i8.p0i8(i8* @sc, i8 11) ; [#uses=1] + store i8 %90, i8* @sc, align 1 + %91 = call i8 @llvm.atomic.load.nand.i8.p0i8(i8* @uc, i8 11) ; [#uses=1] + store i8 %91, i8* @uc, align 1 + %92 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %93 = call i16 @llvm.atomic.load.nand.i16.p0i16(i16* %92, i16 11) ; [#uses=1] + store i16 %93, i16* @ss, align 2 + %94 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %95 = call i16 @llvm.atomic.load.nand.i16.p0i16(i16* %94, i16 11) ; [#uses=1] + store i16 %95, i16* @us, align 2 + %96 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %97 = call i32 @llvm.atomic.load.nand.i32.p0i32(i32* %96, i32 11) ; [#uses=1] + store i32 %97, i32* @si, align 4 + %98 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %99 = call i32 @llvm.atomic.load.nand.i32.p0i32(i32* %98, i32 11) ; [#uses=1] + store i32 %99, i32* @ui, align 4 + %100 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %101 = call i32 @llvm.atomic.load.nand.i32.p0i32(i32* %100, i32 11) ; [#uses=1] + store i32 %101, i32* @sl, align 4 + %102 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %103 = call i32 @llvm.atomic.load.nand.i32.p0i32(i32* %102, i32 11) ; [#uses=1] + store i32 %103, i32* @ul, align 4 + %104 = bitcast i8* bitcast (i64* @sll to i8*) to i64* ; [#uses=1] + %105 = call i64 @llvm.atomic.load.nand.i64.p0i64(i64* %104, i64 11) ; [#uses=1] + store i64 %105, i64* @sll, align 8 + %106 = bitcast i8* bitcast (i64* @ull to i8*) to i64* ; [#uses=1] + %107 = call i64 @llvm.atomic.load.nand.i64.p0i64(i64* %106, i64 11) ; [#uses=1] + store i64 %107, i64* @ull, align 8 + br label %return + +return: ; preds = %entry + ret void +} + +define void @test_op_and_fetch() nounwind { +entry: + %0 = load i8* @uc, align 1 ; [#uses=1] + %1 = zext i8 %0 to i32 ; [#uses=1] + %2 = trunc i32 %1 to i8 ; [#uses=2] + %3 = call i8 @llvm.atomic.load.add.i8.p0i8(i8* @sc, i8 %2) ; [#uses=1] + %4 = add i8 %3, %2 ; [#uses=1] + store i8 %4, i8* @sc, align 1 + %5 = load i8* @uc, align 1 ; [#uses=1] + %6 = zext i8 %5 to i32 ; [#uses=1] + %7 = trunc i32 %6 to i8 ; [#uses=2] + %8 = call i8 @llvm.atomic.load.add.i8.p0i8(i8* @uc, i8 %7) ; [#uses=1] + %9 = add i8 %8, %7 ; [#uses=1] + store i8 %9, i8* @uc, align 1 + %10 = load i8* @uc, align 1 ; [#uses=1] + %11 = zext i8 %10 to i32 ; [#uses=1] + %12 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %13 = trunc i32 %11 to i16 ; [#uses=2] + %14 = call i16 @llvm.atomic.load.add.i16.p0i16(i16* %12, i16 %13) ; [#uses=1] + %15 = add i16 %14, %13 ; [#uses=1] + store i16 %15, i16* @ss, align 2 + %16 = load i8* @uc, align 1 ; [#uses=1] + %17 = zext i8 %16 to i32 ; [#uses=1] + %18 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %19 = trunc i32 %17 to i16 ; [#uses=2] + %20 = call i16 @llvm.atomic.load.add.i16.p0i16(i16* %18, i16 %19) ; [#uses=1] + %21 = add i16 %20, %19 ; [#uses=1] + store i16 %21, i16* @us, align 2 + %22 = load i8* @uc, align 1 ; [#uses=1] + %23 = zext i8 %22 to i32 ; [#uses=2] + %24 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %25 = call i32 @llvm.atomic.load.add.i32.p0i32(i32* %24, i32 %23) ; [#uses=1] + %26 = add i32 %25, %23 ; [#uses=1] + store i32 %26, i32* @si, align 4 + %27 = load i8* @uc, align 1 ; [#uses=1] + %28 = zext i8 %27 to i32 ; [#uses=2] + %29 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %30 = call i32 @llvm.atomic.load.add.i32.p0i32(i32* %29, i32 %28) ; [#uses=1] + %31 = add i32 %30, %28 ; [#uses=1] + store i32 %31, i32* @ui, align 4 + %32 = load i8* @uc, align 1 ; [#uses=1] + %33 = zext i8 %32 to i32 ; [#uses=2] + %34 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %35 = call i32 @llvm.atomic.load.add.i32.p0i32(i32* %34, i32 %33) ; [#uses=1] + %36 = add i32 %35, %33 ; [#uses=1] + store i32 %36, i32* @sl, align 4 + %37 = load i8* @uc, align 1 ; [#uses=1] + %38 = zext i8 %37 to i32 ; [#uses=2] + %39 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %40 = call i32 @llvm.atomic.load.add.i32.p0i32(i32* %39, i32 %38) ; [#uses=1] + %41 = add i32 %40, %38 ; [#uses=1] + store i32 %41, i32* @ul, align 4 + %42 = load i8* @uc, align 1 ; [#uses=1] + %43 = zext i8 %42 to i64 ; [#uses=2] + %44 = bitcast i8* bitcast (i64* @sll to i8*) to i64* ; [#uses=1] + %45 = call i64 @llvm.atomic.load.add.i64.p0i64(i64* %44, i64 %43) ; [#uses=1] + %46 = add i64 %45, %43 ; [#uses=1] + store i64 %46, i64* @sll, align 8 + %47 = load i8* @uc, align 1 ; [#uses=1] + %48 = zext i8 %47 to i64 ; [#uses=2] + %49 = bitcast i8* bitcast (i64* @ull to i8*) to i64* ; [#uses=1] + %50 = call i64 @llvm.atomic.load.add.i64.p0i64(i64* %49, i64 %48) ; [#uses=1] + %51 = add i64 %50, %48 ; [#uses=1] + store i64 %51, i64* @ull, align 8 + %52 = load i8* @uc, align 1 ; [#uses=1] + %53 = zext i8 %52 to i32 ; [#uses=1] + %54 = trunc i32 %53 to i8 ; [#uses=2] + %55 = call i8 @llvm.atomic.load.sub.i8.p0i8(i8* @sc, i8 %54) ; [#uses=1] + %56 = sub i8 %55, %54 ; [#uses=1] + store i8 %56, i8* @sc, align 1 + %57 = load i8* @uc, align 1 ; [#uses=1] + %58 = zext i8 %57 to i32 ; [#uses=1] + %59 = trunc i32 %58 to i8 ; [#uses=2] + %60 = call i8 @llvm.atomic.load.sub.i8.p0i8(i8* @uc, i8 %59) ; [#uses=1] + %61 = sub i8 %60, %59 ; [#uses=1] + store i8 %61, i8* @uc, align 1 + %62 = load i8* @uc, align 1 ; [#uses=1] + %63 = zext i8 %62 to i32 ; [#uses=1] + %64 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %65 = trunc i32 %63 to i16 ; [#uses=2] + %66 = call i16 @llvm.atomic.load.sub.i16.p0i16(i16* %64, i16 %65) ; [#uses=1] + %67 = sub i16 %66, %65 ; [#uses=1] + store i16 %67, i16* @ss, align 2 + %68 = load i8* @uc, align 1 ; [#uses=1] + %69 = zext i8 %68 to i32 ; [#uses=1] + %70 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %71 = trunc i32 %69 to i16 ; [#uses=2] + %72 = call i16 @llvm.atomic.load.sub.i16.p0i16(i16* %70, i16 %71) ; [#uses=1] + %73 = sub i16 %72, %71 ; [#uses=1] + store i16 %73, i16* @us, align 2 + %74 = load i8* @uc, align 1 ; [#uses=1] + %75 = zext i8 %74 to i32 ; [#uses=2] + %76 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %77 = call i32 @llvm.atomic.load.sub.i32.p0i32(i32* %76, i32 %75) ; [#uses=1] + %78 = sub i32 %77, %75 ; [#uses=1] + store i32 %78, i32* @si, align 4 + %79 = load i8* @uc, align 1 ; [#uses=1] + %80 = zext i8 %79 to i32 ; [#uses=2] + %81 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %82 = call i32 @llvm.atomic.load.sub.i32.p0i32(i32* %81, i32 %80) ; [#uses=1] + %83 = sub i32 %82, %80 ; [#uses=1] + store i32 %83, i32* @ui, align 4 + %84 = load i8* @uc, align 1 ; [#uses=1] + %85 = zext i8 %84 to i32 ; [#uses=2] + %86 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %87 = call i32 @llvm.atomic.load.sub.i32.p0i32(i32* %86, i32 %85) ; [#uses=1] + %88 = sub i32 %87, %85 ; [#uses=1] + store i32 %88, i32* @sl, align 4 + %89 = load i8* @uc, align 1 ; [#uses=1] + %90 = zext i8 %89 to i32 ; [#uses=2] + %91 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %92 = call i32 @llvm.atomic.load.sub.i32.p0i32(i32* %91, i32 %90) ; [#uses=1] + %93 = sub i32 %92, %90 ; [#uses=1] + store i32 %93, i32* @ul, align 4 + %94 = load i8* @uc, align 1 ; [#uses=1] + %95 = zext i8 %94 to i64 ; [#uses=2] + %96 = bitcast i8* bitcast (i64* @sll to i8*) to i64* ; [#uses=1] + %97 = call i64 @llvm.atomic.load.sub.i64.p0i64(i64* %96, i64 %95) ; [#uses=1] + %98 = sub i64 %97, %95 ; [#uses=1] + store i64 %98, i64* @sll, align 8 + %99 = load i8* @uc, align 1 ; [#uses=1] + %100 = zext i8 %99 to i64 ; [#uses=2] + %101 = bitcast i8* bitcast (i64* @ull to i8*) to i64* ; [#uses=1] + %102 = call i64 @llvm.atomic.load.sub.i64.p0i64(i64* %101, i64 %100) ; [#uses=1] + %103 = sub i64 %102, %100 ; [#uses=1] + store i64 %103, i64* @ull, align 8 + %104 = load i8* @uc, align 1 ; [#uses=1] + %105 = zext i8 %104 to i32 ; [#uses=1] + %106 = trunc i32 %105 to i8 ; [#uses=2] + %107 = call i8 @llvm.atomic.load.or.i8.p0i8(i8* @sc, i8 %106) ; [#uses=1] + %108 = or i8 %107, %106 ; [#uses=1] + store i8 %108, i8* @sc, align 1 + %109 = load i8* @uc, align 1 ; [#uses=1] + %110 = zext i8 %109 to i32 ; [#uses=1] + %111 = trunc i32 %110 to i8 ; [#uses=2] + %112 = call i8 @llvm.atomic.load.or.i8.p0i8(i8* @uc, i8 %111) ; [#uses=1] + %113 = or i8 %112, %111 ; [#uses=1] + store i8 %113, i8* @uc, align 1 + %114 = load i8* @uc, align 1 ; [#uses=1] + %115 = zext i8 %114 to i32 ; [#uses=1] + %116 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %117 = trunc i32 %115 to i16 ; [#uses=2] + %118 = call i16 @llvm.atomic.load.or.i16.p0i16(i16* %116, i16 %117) ; [#uses=1] + %119 = or i16 %118, %117 ; [#uses=1] + store i16 %119, i16* @ss, align 2 + %120 = load i8* @uc, align 1 ; [#uses=1] + %121 = zext i8 %120 to i32 ; [#uses=1] + %122 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %123 = trunc i32 %121 to i16 ; [#uses=2] + %124 = call i16 @llvm.atomic.load.or.i16.p0i16(i16* %122, i16 %123) ; [#uses=1] + %125 = or i16 %124, %123 ; [#uses=1] + store i16 %125, i16* @us, align 2 + %126 = load i8* @uc, align 1 ; [#uses=1] + %127 = zext i8 %126 to i32 ; [#uses=2] + %128 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %129 = call i32 @llvm.atomic.load.or.i32.p0i32(i32* %128, i32 %127) ; [#uses=1] + %130 = or i32 %129, %127 ; [#uses=1] + store i32 %130, i32* @si, align 4 + %131 = load i8* @uc, align 1 ; [#uses=1] + %132 = zext i8 %131 to i32 ; [#uses=2] + %133 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %134 = call i32 @llvm.atomic.load.or.i32.p0i32(i32* %133, i32 %132) ; [#uses=1] + %135 = or i32 %134, %132 ; [#uses=1] + store i32 %135, i32* @ui, align 4 + %136 = load i8* @uc, align 1 ; [#uses=1] + %137 = zext i8 %136 to i32 ; [#uses=2] + %138 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %139 = call i32 @llvm.atomic.load.or.i32.p0i32(i32* %138, i32 %137) ; [#uses=1] + %140 = or i32 %139, %137 ; [#uses=1] + store i32 %140, i32* @sl, align 4 + %141 = load i8* @uc, align 1 ; [#uses=1] + %142 = zext i8 %141 to i32 ; [#uses=2] + %143 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %144 = call i32 @llvm.atomic.load.or.i32.p0i32(i32* %143, i32 %142) ; [#uses=1] + %145 = or i32 %144, %142 ; [#uses=1] + store i32 %145, i32* @ul, align 4 + %146 = load i8* @uc, align 1 ; [#uses=1] + %147 = zext i8 %146 to i64 ; [#uses=2] + %148 = bitcast i8* bitcast (i64* @sll to i8*) to i64* ; [#uses=1] + %149 = call i64 @llvm.atomic.load.or.i64.p0i64(i64* %148, i64 %147) ; [#uses=1] + %150 = or i64 %149, %147 ; [#uses=1] + store i64 %150, i64* @sll, align 8 + %151 = load i8* @uc, align 1 ; [#uses=1] + %152 = zext i8 %151 to i64 ; [#uses=2] + %153 = bitcast i8* bitcast (i64* @ull to i8*) to i64* ; [#uses=1] + %154 = call i64 @llvm.atomic.load.or.i64.p0i64(i64* %153, i64 %152) ; [#uses=1] + %155 = or i64 %154, %152 ; [#uses=1] + store i64 %155, i64* @ull, align 8 + %156 = load i8* @uc, align 1 ; [#uses=1] + %157 = zext i8 %156 to i32 ; [#uses=1] + %158 = trunc i32 %157 to i8 ; [#uses=2] + %159 = call i8 @llvm.atomic.load.xor.i8.p0i8(i8* @sc, i8 %158) ; [#uses=1] + %160 = xor i8 %159, %158 ; [#uses=1] + store i8 %160, i8* @sc, align 1 + %161 = load i8* @uc, align 1 ; [#uses=1] + %162 = zext i8 %161 to i32 ; [#uses=1] + %163 = trunc i32 %162 to i8 ; [#uses=2] + %164 = call i8 @llvm.atomic.load.xor.i8.p0i8(i8* @uc, i8 %163) ; [#uses=1] + %165 = xor i8 %164, %163 ; [#uses=1] + store i8 %165, i8* @uc, align 1 + %166 = load i8* @uc, align 1 ; [#uses=1] + %167 = zext i8 %166 to i32 ; [#uses=1] + %168 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %169 = trunc i32 %167 to i16 ; [#uses=2] + %170 = call i16 @llvm.atomic.load.xor.i16.p0i16(i16* %168, i16 %169) ; [#uses=1] + %171 = xor i16 %170, %169 ; [#uses=1] + store i16 %171, i16* @ss, align 2 + %172 = load i8* @uc, align 1 ; [#uses=1] + %173 = zext i8 %172 to i32 ; [#uses=1] + %174 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %175 = trunc i32 %173 to i16 ; [#uses=2] + %176 = call i16 @llvm.atomic.load.xor.i16.p0i16(i16* %174, i16 %175) ; [#uses=1] + %177 = xor i16 %176, %175 ; [#uses=1] + store i16 %177, i16* @us, align 2 + %178 = load i8* @uc, align 1 ; [#uses=1] + %179 = zext i8 %178 to i32 ; [#uses=2] + %180 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %181 = call i32 @llvm.atomic.load.xor.i32.p0i32(i32* %180, i32 %179) ; [#uses=1] + %182 = xor i32 %181, %179 ; [#uses=1] + store i32 %182, i32* @si, align 4 + %183 = load i8* @uc, align 1 ; [#uses=1] + %184 = zext i8 %183 to i32 ; [#uses=2] + %185 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %186 = call i32 @llvm.atomic.load.xor.i32.p0i32(i32* %185, i32 %184) ; [#uses=1] + %187 = xor i32 %186, %184 ; [#uses=1] + store i32 %187, i32* @ui, align 4 + %188 = load i8* @uc, align 1 ; [#uses=1] + %189 = zext i8 %188 to i32 ; [#uses=2] + %190 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %191 = call i32 @llvm.atomic.load.xor.i32.p0i32(i32* %190, i32 %189) ; [#uses=1] + %192 = xor i32 %191, %189 ; [#uses=1] + store i32 %192, i32* @sl, align 4 + %193 = load i8* @uc, align 1 ; [#uses=1] + %194 = zext i8 %193 to i32 ; [#uses=2] + %195 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %196 = call i32 @llvm.atomic.load.xor.i32.p0i32(i32* %195, i32 %194) ; [#uses=1] + %197 = xor i32 %196, %194 ; [#uses=1] + store i32 %197, i32* @ul, align 4 + %198 = load i8* @uc, align 1 ; [#uses=1] + %199 = zext i8 %198 to i64 ; [#uses=2] + %200 = bitcast i8* bitcast (i64* @sll to i8*) to i64* ; [#uses=1] + %201 = call i64 @llvm.atomic.load.xor.i64.p0i64(i64* %200, i64 %199) ; [#uses=1] + %202 = xor i64 %201, %199 ; [#uses=1] + store i64 %202, i64* @sll, align 8 + %203 = load i8* @uc, align 1 ; [#uses=1] + %204 = zext i8 %203 to i64 ; [#uses=2] + %205 = bitcast i8* bitcast (i64* @ull to i8*) to i64* ; [#uses=1] + %206 = call i64 @llvm.atomic.load.xor.i64.p0i64(i64* %205, i64 %204) ; [#uses=1] + %207 = xor i64 %206, %204 ; [#uses=1] + store i64 %207, i64* @ull, align 8 + %208 = load i8* @uc, align 1 ; [#uses=1] + %209 = zext i8 %208 to i32 ; [#uses=1] + %210 = trunc i32 %209 to i8 ; [#uses=2] + %211 = call i8 @llvm.atomic.load.and.i8.p0i8(i8* @sc, i8 %210) ; [#uses=1] + %212 = and i8 %211, %210 ; [#uses=1] + store i8 %212, i8* @sc, align 1 + %213 = load i8* @uc, align 1 ; [#uses=1] + %214 = zext i8 %213 to i32 ; [#uses=1] + %215 = trunc i32 %214 to i8 ; [#uses=2] + %216 = call i8 @llvm.atomic.load.and.i8.p0i8(i8* @uc, i8 %215) ; [#uses=1] + %217 = and i8 %216, %215 ; [#uses=1] + store i8 %217, i8* @uc, align 1 + %218 = load i8* @uc, align 1 ; [#uses=1] + %219 = zext i8 %218 to i32 ; [#uses=1] + %220 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %221 = trunc i32 %219 to i16 ; [#uses=2] + %222 = call i16 @llvm.atomic.load.and.i16.p0i16(i16* %220, i16 %221) ; [#uses=1] + %223 = and i16 %222, %221 ; [#uses=1] + store i16 %223, i16* @ss, align 2 + %224 = load i8* @uc, align 1 ; [#uses=1] + %225 = zext i8 %224 to i32 ; [#uses=1] + %226 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %227 = trunc i32 %225 to i16 ; [#uses=2] + %228 = call i16 @llvm.atomic.load.and.i16.p0i16(i16* %226, i16 %227) ; [#uses=1] + %229 = and i16 %228, %227 ; [#uses=1] + store i16 %229, i16* @us, align 2 + %230 = load i8* @uc, align 1 ; [#uses=1] + %231 = zext i8 %230 to i32 ; [#uses=2] + %232 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %233 = call i32 @llvm.atomic.load.and.i32.p0i32(i32* %232, i32 %231) ; [#uses=1] + %234 = and i32 %233, %231 ; [#uses=1] + store i32 %234, i32* @si, align 4 + %235 = load i8* @uc, align 1 ; [#uses=1] + %236 = zext i8 %235 to i32 ; [#uses=2] + %237 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %238 = call i32 @llvm.atomic.load.and.i32.p0i32(i32* %237, i32 %236) ; [#uses=1] + %239 = and i32 %238, %236 ; [#uses=1] + store i32 %239, i32* @ui, align 4 + %240 = load i8* @uc, align 1 ; [#uses=1] + %241 = zext i8 %240 to i32 ; [#uses=2] + %242 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %243 = call i32 @llvm.atomic.load.and.i32.p0i32(i32* %242, i32 %241) ; [#uses=1] + %244 = and i32 %243, %241 ; [#uses=1] + store i32 %244, i32* @sl, align 4 + %245 = load i8* @uc, align 1 ; [#uses=1] + %246 = zext i8 %245 to i32 ; [#uses=2] + %247 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %248 = call i32 @llvm.atomic.load.and.i32.p0i32(i32* %247, i32 %246) ; [#uses=1] + %249 = and i32 %248, %246 ; [#uses=1] + store i32 %249, i32* @ul, align 4 + %250 = load i8* @uc, align 1 ; [#uses=1] + %251 = zext i8 %250 to i64 ; [#uses=2] + %252 = bitcast i8* bitcast (i64* @sll to i8*) to i64* ; [#uses=1] + %253 = call i64 @llvm.atomic.load.and.i64.p0i64(i64* %252, i64 %251) ; [#uses=1] + %254 = and i64 %253, %251 ; [#uses=1] + store i64 %254, i64* @sll, align 8 + %255 = load i8* @uc, align 1 ; [#uses=1] + %256 = zext i8 %255 to i64 ; [#uses=2] + %257 = bitcast i8* bitcast (i64* @ull to i8*) to i64* ; [#uses=1] + %258 = call i64 @llvm.atomic.load.and.i64.p0i64(i64* %257, i64 %256) ; [#uses=1] + %259 = and i64 %258, %256 ; [#uses=1] + store i64 %259, i64* @ull, align 8 + %260 = load i8* @uc, align 1 ; [#uses=1] + %261 = zext i8 %260 to i32 ; [#uses=1] + %262 = trunc i32 %261 to i8 ; [#uses=2] + %263 = call i8 @llvm.atomic.load.nand.i8.p0i8(i8* @sc, i8 %262) ; [#uses=1] + %264 = xor i8 %263, -1 ; [#uses=1] + %265 = and i8 %264, %262 ; [#uses=1] + store i8 %265, i8* @sc, align 1 + %266 = load i8* @uc, align 1 ; [#uses=1] + %267 = zext i8 %266 to i32 ; [#uses=1] + %268 = trunc i32 %267 to i8 ; [#uses=2] + %269 = call i8 @llvm.atomic.load.nand.i8.p0i8(i8* @uc, i8 %268) ; [#uses=1] + %270 = xor i8 %269, -1 ; [#uses=1] + %271 = and i8 %270, %268 ; [#uses=1] + store i8 %271, i8* @uc, align 1 + %272 = load i8* @uc, align 1 ; [#uses=1] + %273 = zext i8 %272 to i32 ; [#uses=1] + %274 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %275 = trunc i32 %273 to i16 ; [#uses=2] + %276 = call i16 @llvm.atomic.load.nand.i16.p0i16(i16* %274, i16 %275) ; [#uses=1] + %277 = xor i16 %276, -1 ; [#uses=1] + %278 = and i16 %277, %275 ; [#uses=1] + store i16 %278, i16* @ss, align 2 + %279 = load i8* @uc, align 1 ; [#uses=1] + %280 = zext i8 %279 to i32 ; [#uses=1] + %281 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %282 = trunc i32 %280 to i16 ; [#uses=2] + %283 = call i16 @llvm.atomic.load.nand.i16.p0i16(i16* %281, i16 %282) ; [#uses=1] + %284 = xor i16 %283, -1 ; [#uses=1] + %285 = and i16 %284, %282 ; [#uses=1] + store i16 %285, i16* @us, align 2 + %286 = load i8* @uc, align 1 ; [#uses=1] + %287 = zext i8 %286 to i32 ; [#uses=2] + %288 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %289 = call i32 @llvm.atomic.load.nand.i32.p0i32(i32* %288, i32 %287) ; [#uses=1] + %290 = xor i32 %289, -1 ; [#uses=1] + %291 = and i32 %290, %287 ; [#uses=1] + store i32 %291, i32* @si, align 4 + %292 = load i8* @uc, align 1 ; [#uses=1] + %293 = zext i8 %292 to i32 ; [#uses=2] + %294 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %295 = call i32 @llvm.atomic.load.nand.i32.p0i32(i32* %294, i32 %293) ; [#uses=1] + %296 = xor i32 %295, -1 ; [#uses=1] + %297 = and i32 %296, %293 ; [#uses=1] + store i32 %297, i32* @ui, align 4 + %298 = load i8* @uc, align 1 ; [#uses=1] + %299 = zext i8 %298 to i32 ; [#uses=2] + %300 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %301 = call i32 @llvm.atomic.load.nand.i32.p0i32(i32* %300, i32 %299) ; [#uses=1] + %302 = xor i32 %301, -1 ; [#uses=1] + %303 = and i32 %302, %299 ; [#uses=1] + store i32 %303, i32* @sl, align 4 + %304 = load i8* @uc, align 1 ; [#uses=1] + %305 = zext i8 %304 to i32 ; [#uses=2] + %306 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %307 = call i32 @llvm.atomic.load.nand.i32.p0i32(i32* %306, i32 %305) ; [#uses=1] + %308 = xor i32 %307, -1 ; [#uses=1] + %309 = and i32 %308, %305 ; [#uses=1] + store i32 %309, i32* @ul, align 4 + %310 = load i8* @uc, align 1 ; [#uses=1] + %311 = zext i8 %310 to i64 ; [#uses=2] + %312 = bitcast i8* bitcast (i64* @sll to i8*) to i64* ; [#uses=1] + %313 = call i64 @llvm.atomic.load.nand.i64.p0i64(i64* %312, i64 %311) ; [#uses=1] + %314 = xor i64 %313, -1 ; [#uses=1] + %315 = and i64 %314, %311 ; [#uses=1] + store i64 %315, i64* @sll, align 8 + %316 = load i8* @uc, align 1 ; [#uses=1] + %317 = zext i8 %316 to i64 ; [#uses=2] + %318 = bitcast i8* bitcast (i64* @ull to i8*) to i64* ; [#uses=1] + %319 = call i64 @llvm.atomic.load.nand.i64.p0i64(i64* %318, i64 %317) ; [#uses=1] + %320 = xor i64 %319, -1 ; [#uses=1] + %321 = and i64 %320, %317 ; [#uses=1] + store i64 %321, i64* @ull, align 8 + br label %return + +return: ; preds = %entry + ret void +} + +define void @test_compare_and_swap() nounwind { +entry: + %0 = load i8* @sc, align 1 ; [#uses=1] + %1 = zext i8 %0 to i32 ; [#uses=1] + %2 = load i8* @uc, align 1 ; [#uses=1] + %3 = zext i8 %2 to i32 ; [#uses=1] + %4 = trunc i32 %3 to i8 ; [#uses=1] + %5 = trunc i32 %1 to i8 ; [#uses=1] + %6 = call i8 @llvm.atomic.cmp.swap.i8.p0i8(i8* @sc, i8 %4, i8 %5) ; [#uses=1] + store i8 %6, i8* @sc, align 1 + %7 = load i8* @sc, align 1 ; [#uses=1] + %8 = zext i8 %7 to i32 ; [#uses=1] + %9 = load i8* @uc, align 1 ; [#uses=1] + %10 = zext i8 %9 to i32 ; [#uses=1] + %11 = trunc i32 %10 to i8 ; [#uses=1] + %12 = trunc i32 %8 to i8 ; [#uses=1] + %13 = call i8 @llvm.atomic.cmp.swap.i8.p0i8(i8* @uc, i8 %11, i8 %12) ; [#uses=1] + store i8 %13, i8* @uc, align 1 + %14 = load i8* @sc, align 1 ; [#uses=1] + %15 = sext i8 %14 to i16 ; [#uses=1] + %16 = zext i16 %15 to i32 ; [#uses=1] + %17 = load i8* @uc, align 1 ; [#uses=1] + %18 = zext i8 %17 to i32 ; [#uses=1] + %19 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %20 = trunc i32 %18 to i16 ; [#uses=1] + %21 = trunc i32 %16 to i16 ; [#uses=1] + %22 = call i16 @llvm.atomic.cmp.swap.i16.p0i16(i16* %19, i16 %20, i16 %21) ; [#uses=1] + store i16 %22, i16* @ss, align 2 + %23 = load i8* @sc, align 1 ; [#uses=1] + %24 = sext i8 %23 to i16 ; [#uses=1] + %25 = zext i16 %24 to i32 ; [#uses=1] + %26 = load i8* @uc, align 1 ; [#uses=1] + %27 = zext i8 %26 to i32 ; [#uses=1] + %28 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %29 = trunc i32 %27 to i16 ; [#uses=1] + %30 = trunc i32 %25 to i16 ; [#uses=1] + %31 = call i16 @llvm.atomic.cmp.swap.i16.p0i16(i16* %28, i16 %29, i16 %30) ; [#uses=1] + store i16 %31, i16* @us, align 2 + %32 = load i8* @sc, align 1 ; [#uses=1] + %33 = sext i8 %32 to i32 ; [#uses=1] + %34 = load i8* @uc, align 1 ; [#uses=1] + %35 = zext i8 %34 to i32 ; [#uses=1] + %36 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %37 = call i32 @llvm.atomic.cmp.swap.i32.p0i32(i32* %36, i32 %35, i32 %33) ; [#uses=1] + store i32 %37, i32* @si, align 4 + %38 = load i8* @sc, align 1 ; [#uses=1] + %39 = sext i8 %38 to i32 ; [#uses=1] + %40 = load i8* @uc, align 1 ; [#uses=1] + %41 = zext i8 %40 to i32 ; [#uses=1] + %42 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %43 = call i32 @llvm.atomic.cmp.swap.i32.p0i32(i32* %42, i32 %41, i32 %39) ; [#uses=1] + store i32 %43, i32* @ui, align 4 + %44 = load i8* @sc, align 1 ; [#uses=1] + %45 = sext i8 %44 to i32 ; [#uses=1] + %46 = load i8* @uc, align 1 ; [#uses=1] + %47 = zext i8 %46 to i32 ; [#uses=1] + %48 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %49 = call i32 @llvm.atomic.cmp.swap.i32.p0i32(i32* %48, i32 %47, i32 %45) ; [#uses=1] + store i32 %49, i32* @sl, align 4 + %50 = load i8* @sc, align 1 ; [#uses=1] + %51 = sext i8 %50 to i32 ; [#uses=1] + %52 = load i8* @uc, align 1 ; [#uses=1] + %53 = zext i8 %52 to i32 ; [#uses=1] + %54 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %55 = call i32 @llvm.atomic.cmp.swap.i32.p0i32(i32* %54, i32 %53, i32 %51) ; [#uses=1] + store i32 %55, i32* @ul, align 4 + %56 = load i8* @sc, align 1 ; [#uses=1] + %57 = zext i8 %56 to i32 ; [#uses=1] + %58 = load i8* @uc, align 1 ; [#uses=1] + %59 = zext i8 %58 to i32 ; [#uses=1] + %60 = trunc i32 %59 to i8 ; [#uses=2] + %61 = trunc i32 %57 to i8 ; [#uses=1] + %62 = call i8 @llvm.atomic.cmp.swap.i8.p0i8(i8* @sc, i8 %60, i8 %61) ; [#uses=1] + %63 = icmp eq i8 %62, %60 ; [#uses=1] + %64 = zext i1 %63 to i8 ; [#uses=1] + %65 = zext i8 %64 to i32 ; [#uses=1] + store i32 %65, i32* @ui, align 4 + %66 = load i8* @sc, align 1 ; [#uses=1] + %67 = zext i8 %66 to i32 ; [#uses=1] + %68 = load i8* @uc, align 1 ; [#uses=1] + %69 = zext i8 %68 to i32 ; [#uses=1] + %70 = trunc i32 %69 to i8 ; [#uses=2] + %71 = trunc i32 %67 to i8 ; [#uses=1] + %72 = call i8 @llvm.atomic.cmp.swap.i8.p0i8(i8* @uc, i8 %70, i8 %71) ; [#uses=1] + %73 = icmp eq i8 %72, %70 ; [#uses=1] + %74 = zext i1 %73 to i8 ; [#uses=1] + %75 = zext i8 %74 to i32 ; [#uses=1] + store i32 %75, i32* @ui, align 4 + %76 = load i8* @sc, align 1 ; [#uses=1] + %77 = sext i8 %76 to i16 ; [#uses=1] + %78 = zext i16 %77 to i32 ; [#uses=1] + %79 = load i8* @uc, align 1 ; [#uses=1] + %80 = zext i8 %79 to i32 ; [#uses=1] + %81 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %82 = trunc i32 %80 to i16 ; [#uses=2] + %83 = trunc i32 %78 to i16 ; [#uses=1] + %84 = call i16 @llvm.atomic.cmp.swap.i16.p0i16(i16* %81, i16 %82, i16 %83) ; [#uses=1] + %85 = icmp eq i16 %84, %82 ; [#uses=1] + %86 = zext i1 %85 to i8 ; [#uses=1] + %87 = zext i8 %86 to i32 ; [#uses=1] + store i32 %87, i32* @ui, align 4 + %88 = load i8* @sc, align 1 ; [#uses=1] + %89 = sext i8 %88 to i16 ; [#uses=1] + %90 = zext i16 %89 to i32 ; [#uses=1] + %91 = load i8* @uc, align 1 ; [#uses=1] + %92 = zext i8 %91 to i32 ; [#uses=1] + %93 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %94 = trunc i32 %92 to i16 ; [#uses=2] + %95 = trunc i32 %90 to i16 ; [#uses=1] + %96 = call i16 @llvm.atomic.cmp.swap.i16.p0i16(i16* %93, i16 %94, i16 %95) ; [#uses=1] + %97 = icmp eq i16 %96, %94 ; [#uses=1] + %98 = zext i1 %97 to i8 ; [#uses=1] + %99 = zext i8 %98 to i32 ; [#uses=1] + store i32 %99, i32* @ui, align 4 + %100 = load i8* @sc, align 1 ; [#uses=1] + %101 = sext i8 %100 to i32 ; [#uses=1] + %102 = load i8* @uc, align 1 ; [#uses=1] + %103 = zext i8 %102 to i32 ; [#uses=2] + %104 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %105 = call i32 @llvm.atomic.cmp.swap.i32.p0i32(i32* %104, i32 %103, i32 %101) ; [#uses=1] + %106 = icmp eq i32 %105, %103 ; [#uses=1] + %107 = zext i1 %106 to i8 ; [#uses=1] + %108 = zext i8 %107 to i32 ; [#uses=1] + store i32 %108, i32* @ui, align 4 + %109 = load i8* @sc, align 1 ; [#uses=1] + %110 = sext i8 %109 to i32 ; [#uses=1] + %111 = load i8* @uc, align 1 ; [#uses=1] + %112 = zext i8 %111 to i32 ; [#uses=2] + %113 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %114 = call i32 @llvm.atomic.cmp.swap.i32.p0i32(i32* %113, i32 %112, i32 %110) ; [#uses=1] + %115 = icmp eq i32 %114, %112 ; [#uses=1] + %116 = zext i1 %115 to i8 ; [#uses=1] + %117 = zext i8 %116 to i32 ; [#uses=1] + store i32 %117, i32* @ui, align 4 + %118 = load i8* @sc, align 1 ; [#uses=1] + %119 = sext i8 %118 to i32 ; [#uses=1] + %120 = load i8* @uc, align 1 ; [#uses=1] + %121 = zext i8 %120 to i32 ; [#uses=2] + %122 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %123 = call i32 @llvm.atomic.cmp.swap.i32.p0i32(i32* %122, i32 %121, i32 %119) ; [#uses=1] + %124 = icmp eq i32 %123, %121 ; [#uses=1] + %125 = zext i1 %124 to i8 ; [#uses=1] + %126 = zext i8 %125 to i32 ; [#uses=1] + store i32 %126, i32* @ui, align 4 + %127 = load i8* @sc, align 1 ; [#uses=1] + %128 = sext i8 %127 to i32 ; [#uses=1] + %129 = load i8* @uc, align 1 ; [#uses=1] + %130 = zext i8 %129 to i32 ; [#uses=2] + %131 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %132 = call i32 @llvm.atomic.cmp.swap.i32.p0i32(i32* %131, i32 %130, i32 %128) ; [#uses=1] + %133 = icmp eq i32 %132, %130 ; [#uses=1] + %134 = zext i1 %133 to i8 ; [#uses=1] + %135 = zext i8 %134 to i32 ; [#uses=1] + store i32 %135, i32* @ui, align 4 + br label %return + +return: ; preds = %entry + ret void +} + +declare i8 @llvm.atomic.cmp.swap.i8.p0i8(i8*, i8, i8) nounwind + +declare i16 @llvm.atomic.cmp.swap.i16.p0i16(i16*, i16, i16) nounwind + +declare i32 @llvm.atomic.cmp.swap.i32.p0i32(i32*, i32, i32) nounwind + +define void @test_lock() nounwind { +entry: + %0 = call i8 @llvm.atomic.swap.i8.p0i8(i8* @sc, i8 1) ; [#uses=1] + store i8 %0, i8* @sc, align 1 + %1 = call i8 @llvm.atomic.swap.i8.p0i8(i8* @uc, i8 1) ; [#uses=1] + store i8 %1, i8* @uc, align 1 + %2 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + %3 = call i16 @llvm.atomic.swap.i16.p0i16(i16* %2, i16 1) ; [#uses=1] + store i16 %3, i16* @ss, align 2 + %4 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + %5 = call i16 @llvm.atomic.swap.i16.p0i16(i16* %4, i16 1) ; [#uses=1] + store i16 %5, i16* @us, align 2 + %6 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + %7 = call i32 @llvm.atomic.swap.i32.p0i32(i32* %6, i32 1) ; [#uses=1] + store i32 %7, i32* @si, align 4 + %8 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + %9 = call i32 @llvm.atomic.swap.i32.p0i32(i32* %8, i32 1) ; [#uses=1] + store i32 %9, i32* @ui, align 4 + %10 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + %11 = call i32 @llvm.atomic.swap.i32.p0i32(i32* %10, i32 1) ; [#uses=1] + store i32 %11, i32* @sl, align 4 + %12 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + %13 = call i32 @llvm.atomic.swap.i32.p0i32(i32* %12, i32 1) ; [#uses=1] + store i32 %13, i32* @ul, align 4 + call void @llvm.memory.barrier(i1 true, i1 true, i1 true, i1 true, i1 false) + volatile store i8 0, i8* @sc, align 1 + volatile store i8 0, i8* @uc, align 1 + %14 = bitcast i8* bitcast (i16* @ss to i8*) to i16* ; [#uses=1] + volatile store i16 0, i16* %14, align 2 + %15 = bitcast i8* bitcast (i16* @us to i8*) to i16* ; [#uses=1] + volatile store i16 0, i16* %15, align 2 + %16 = bitcast i8* bitcast (i32* @si to i8*) to i32* ; [#uses=1] + volatile store i32 0, i32* %16, align 4 + %17 = bitcast i8* bitcast (i32* @ui to i8*) to i32* ; [#uses=1] + volatile store i32 0, i32* %17, align 4 + %18 = bitcast i8* bitcast (i32* @sl to i8*) to i32* ; [#uses=1] + volatile store i32 0, i32* %18, align 4 + %19 = bitcast i8* bitcast (i32* @ul to i8*) to i32* ; [#uses=1] + volatile store i32 0, i32* %19, align 4 + %20 = bitcast i8* bitcast (i64* @sll to i8*) to i64* ; [#uses=1] + volatile store i64 0, i64* %20, align 8 + %21 = bitcast i8* bitcast (i64* @ull to i8*) to i64* ; [#uses=1] + volatile store i64 0, i64* %21, align 8 + br label %return + +return: ; preds = %entry + ret void +} + +declare i8 @llvm.atomic.swap.i8.p0i8(i8*, i8) nounwind + +declare i16 @llvm.atomic.swap.i16.p0i16(i16*, i16) nounwind + +declare i32 @llvm.atomic.swap.i32.p0i32(i32*, i32) nounwind + +declare void @llvm.memory.barrier(i1, i1, i1, i1, i1) nounwind diff --git a/llvm/utils/TableGen/CodeGenInstruction.cpp b/llvm/utils/TableGen/CodeGenInstruction.cpp index 37c2069ec727..2a5b0bf99b40 100644 --- a/llvm/utils/TableGen/CodeGenInstruction.cpp +++ b/llvm/utils/TableGen/CodeGenInstruction.cpp @@ -21,7 +21,8 @@ static void ParseConstraint(const std::string &CStr, CodeGenInstruction *I) { // FIXME: Only supports TIED_TO for now. std::string::size_type pos = CStr.find_first_of('='); assert(pos != std::string::npos && "Unrecognized constraint"); - std::string Name = CStr.substr(0, pos); + std::string::size_type start = CStr.find_first_not_of(" \t"); + std::string Name = CStr.substr(start, pos); // TIED_TO: $src1 = $dst std::string::size_type wpos = Name.find_first_of(" \t");